Bitfusion offer cloud-based access to FPGA hardware acceleration using Xilinx All Programmable devices

2015年11月26日 | By News | Filed in: News.


This was inevitable. Someone was bound to offer cloud-based access to FPGA hardware acceleration.

Enter Bitfusion.

Bitfusion develops software, designs hardware, and creates data centers dedicated to accelerating cloud-based computing (in partnership with Rackspace). As the concept applies to FPGA-based hardware acceleration, Bitfusion is developing hardware accelerators based on Xilinx All Programmable devices and will provide cloud-based development tools based on Xilinx tools that allow customers to access hardware-based acceleration as a service for HPC (high-performance computing).

I spoke with Subbu Rama last week in his company’s booth at SC15 in Austin. Rama is CEO and a founder of Bitfusion. His vision is to allow anyone with a laptop to solve HPC-class problems by providing easy, on-demand access to a variety of integrated cloud-based tools including FPGA-based hardware acceleration. Bitfusion charges you for the number of kernel function calls and the kernels’ execution time, and not development time.

Bitfuion initially focused on OpenCL applications but the Bitfusion Cloud Adaptor that the company launched last week at SC15 also handles a variety of other programming languages through OpenCL bindings available from other sources including: C, C++, and Objective C; Delphi/Pascal; Fortran; Go; Java; Javascript; Julia; LISP; Mathematica; MATLAB; .NET, C#, F#, and Visual Basic; Perl; Python; R; Ruby; and Rust.

Your preferred language should be in there somewhere.

Bitfusion has also developed several example applications including:

  • Vector addition – a simple vector addition, more like a hello world for beginners.
  • SmithWaterman – implements the Bioinformatics Smith Waterman algorithm in FPGA.
  • BLASTP – implements the Bioinformatics Sequence Alignment application BLASTP in FPGA.
  • Regular Expression – implements grep-like regular expression parsing.
  • Blowfish – an implementation of Blowfish encryption.
  • JPEG Decode – an implementation of JPEG image compression.
  • SHA – implements the Secure Hash Algorithm, a cryptographic hash function.
  • Adaptive Differential Pulse Code Modulation Algorithm (ADPCM) – an implementation of ITU G.722 Adaptive Differential Pulse-Code Modulation (ADPCM) algorithm used to encode/decode audio signals. ADPCM is often used in Voice over IP communications.
  • Motion Vector Decoding – implements MPEG-2 motion-vector decoding.

Here’s a TechCrunch Disrupt video from May with a more detailed explanation of Bitfusion’s idea:


电子邮件地址不会被公开。 必填项已用*标注